Premium
Maxentropic Reconstruction of Some Probability Distributions
Author(s) -
Gzyl Henryk
Publication year - 2000
Publication title -
studies in applied mathematics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.164
H-Index - 46
eISSN - 1467-9590
pISSN - 0022-2526
DOI - 10.1111/1467-9590.00150
Subject(s) - mathematics , probability distribution , principle of maximum entropy , inverse distribution , entropy (arrow of time) , inverse , inverse problem , convolution of probability distributions , statistical physics , mathematical analysis , heavy tailed distribution , statistics , probability mass function , geometry , physics , quantum mechanics
We propose a variational method to describe some families of probability distributions. The given probability distributions are to be found from the knowledge of the expected values of some variables. To do that we restate the problem as a constrained linear inverse problem, which we then proceed to solve by the method of maximum entropy on the mean.